AI Paper Atlas

Research map / 3D vision / 3D generation

OmniNWM: Unifying the State-Action-Reward Triad for Closed-Loop Panoramic Driving Navigation World Models

Bohan Li, Zhuang Ma, Dalong Du, Baorui Peng, Zhujin Liang, Zhenqiang Liu, Xianda Guo, Chao Ma, Yueming Jin, Zheng Zhu, HAO ZHAO, Wenjun Zeng and 1 more

ECCV 2026 · 3D vision › 3D generation · approach: Scene-aware human motion synthesis

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add canonical panoramic ray-map normalization (ablation)OmniNWM · nuScenes camera controlTransErr (m): 9.75 -> 1.18Improved
add canonical panoramic ray-map normalization (ablation)OmniNWM · nuScenes camera controlRotErr (rad): 1.71 -> 0.16Improved
add structured panoramic forcing instead of pure autoregression (ablation)OmniNWM · nuScenes 201-frame generationFVD201: 386.72 -> 25.22Improved
use structured noise instead of standard scheduled sampling (ablation)OmniNWM · nuScenes 201-frame generationFVD201: 178.65 -> 25.22Improved
add unstructured scheduled sampling noise to pure autoregression (ablation)OmniNWM · nuScenes 201-frame generationFVD201: 386.72 -> 178.65Improved
add generated semantics and depth as occupancy inputs (ablation)OmniNWM occupancy generator · nuScenes-OccupancymIoU: 3.0 and 2.7 mIoUImproved
OmniNWM vs UniScene on video qualityOmniNWM · nuScenes valFVD: 71.94 -> 23.63Improved
OmniNWM vs DiST-4D zero-shot on nuPlanOmniNWM · nuPlan zero-shotTransErr (m): 7.12 -> 1.65Improved
OmniNWM vs Hi-SOP on occupancyOmniNWM · nuScenes-OccupancymIoU: 16.4 -> 19.8Improved
OmniNWM vs M2Depth on panoramic depthOmniNWM · nuScenes val depthAbs. Rel.: 0.26 -> 0.23Improved

Later papers that compared with this method

1 later accepted paper reports OmniNWM as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy